Abstract: An embodiment of the system for publishing events of a telephony application to a client includes a call router that generates events from the telephony application and an event router that manages the publication of events generated by the call router and that manages the subscription to events by clients. The system can be used with a telephony application that interfaces with a telephony device and an application server.

Abstract: An approach is disclosed that provides personalized two-way communication with a uniquely identified object and an AI agent. Information about the object in a context associated with a requestor is received to access to an object knowledge base. The information is analyzed to determine a unique reference for the object. A selected set of the received information and the object categorization may be sent to an object knowledge base populated with AI configuration parameters tied to uniquely identified objects. The object knowledge base is searched for the unique reference to determine a registration assessment. The registration assessment is one of registered and not registered. When the registration assessment is determined to be not registered, the object is added to the object knowledge base. After receiving an AI connection from the object knowledge base, the context associated with the requestor is sent to the AI connection.

Abstract: An embodiment of the system for publishing events of a telephony application to a client includes a call router that generates events from the telephony application and an event router that manages the publication of events generated by the call router and that manages the subscription to events by clients. The system can be used with a telephony application that interfaces with a telephony device and an application server.

Abstract: A call captioning system for captioning a hearing user's (HU's) voice signal during an ongoing call with an assisted user (AU) includes: an AU communication device with a display screen and a caption service activation feature, and a first processor programmed to, during an ongoing call, receive the HU's voice signal. Prior to activating the caption service via the activation feature, the processor uses an automated speech recognition (ASR) engine to generate HU voice signal captions, detect errors in the HU voice signal captions, use the errors to train the ASR software to the HU's voice signal to increase accuracy of the HU captions generated by the ASR engine; and store the trained ASR engine for subsequent use. Upon activating the caption service during the ongoing call, the processor uses the trained ASR engine to generate HU voice signal captions and present them to the AU via the display screen.

Abstract: Systems and methods are used to generate contact type predictions that route user customer service requests within a support platform. The contact type predictions are generated using a hybrid model that includes a deep learning component and a business logic component. The deep learning component may generate a multi-channel output based on text features and context features. The multi-channel output is modified based on one or more business rules to generate the contact type predictions.

Abstract: Apparatuses and methods concerning providing a data-communications virtual assistant are disclosed. As an example, one apparatus includes a data-communications server. The data communications server is configured to process user-data-communication between a client station and another client station participating in data-communications via the data-communications server, where each client station is associated with one client entity. The server is also configured to identify a context for each user-data-communication between the client station and the other client station, where the context corresponds to at least one communications-specific characteristic associated with the user-data-communication. The server is further configured to apply call routing based on the identified context.

Abstract: A computerized-method for providing real-time lockless parallel screen recording compliance enforcement to omni-channel cloud systems, is provided herein. In a processor of a client computer configured to execute code for recording events of one or more voice or digital interactions, on one or more screens associated to the client computer, the computerized-method maintains a cache for storing a masked state. Each interaction is having an associated interaction identifier and upon receiving a screen event from a server of a cloud-based video recording that is communicating with the client computer over a communication network, operating a compliance-enforcement module. The compliance-enforcement module includes updating the cache; and operating a module of recording of screen events for the screen events of the one or more voice or digital interactions. Thus, by updating in real-time the cache on the client computer refraining from database locks in the server of the cloud-based video recording.

Abstract: A system and method for omnichannel text-based routing and customer-to-enterprise communications. The system comprises an interaction control system, an interaction routing system, and a media translation system. The system takes in requests from customers to text, email, or chat with a businessperson and facilitates the interaction by routing, masking, and converting where necessary. The routing is selected from a list of various algorithms and methods to determine the best businessperson to route the customer to. Masking by the system holds anonymity between the customer and businessperson, while conversion happens when the customer and businessperson are using two different communication vehicles such as from text messaging to email.

Abstract: A non-transitory computer-readable recording medium storing an estimation program that causes a processor included in a computer to execute a process. The process includes receiving a message of an estimation target of a forwarding destination, searching past messages for a message similar to the received message, estimating, when there is no similar message among the past massage, the forwarding destination of the message using a model of estimating the forwarding destination based on a keyword that is identified based on a word included in the received message, and outputting a forwarding destination of the searched similar message or the estimated forwarding destination.

Abstract: A system is provided for streaming broadcast media content between peer devices in a media distribution network. The system includes a virtual router panel that includes a notification service controller that receives a data communication request from two or more peer devices and a data communication handshaking controller selects a delivery protocol between the two devices based on exchanging communication candidates that identify peer addresses. A media streaming tunnel generator establishes a streaming tunnel between the first device and the second device based on the respective delivery protocol selected by the data communication handshaking controller; and an encoder packetizes video, audio and ancillary grains directly as packets of the broadcast media content to be streamed directly from the first device to the second device via the established streaming tunnel without multiplexing.

Abstract: A system and method provide an automation solution for guiding a contact center agent during a communication session by providing contextual in-line assistance. Robotic process automation (RPA) is used for automating workflows and processes with robots that capture information from multiple applications of a contact center system and generate contextual guidance for the contact center agent via callout activities during the communication session.

Abstract: A device receives real-time data and historical data associated with a product or a service, wherein the real-time data includes data indicating real-time interactions between customers of the product or the service and customer service personnel. The device processes the real-time data and the historical data to generate processed data, and utilizes a first artificial intelligence model with the processed data to determine future events associated with the product or the service, and preventative solutions for the future events. The device extracts one or more features from the processed data to provide extracted features, and utilizes a second artificial intelligence model with the extracted features to determine priorities associated with the preventative solutions. The device performs one or more particular preventative solutions based on the priorities associated with the preventative solutions.

Abstract: A method and system for analyzing interactions (for example between a person and an organization) may include for a number of series of interactions (which may be termed journeys), each interaction represented by a channel and a reason, iterating over the series of interactions by selecting initial information including an interaction subset including one or more interactions, and if there is a set of interaction series among the series of interactions meeting certain conditions, adding an interaction to the interaction subset and determining in a recursive fashion if for the interaction subset, there is a subset among the set of interaction series meeting the conditions which also meet the conditions. Conditions may include a threshold average rating for the set of interaction series, and a threshold number of interaction series in which the interaction subset is found.

Abstract: Implementations for providing communication services using a virtual environment are described. An audio communication session may be established between a first user device and a second user device. The second user device may answer the audio communication session using a virtual environment. The virtual environment may be updated to display virtual features associated with the communication session.

Abstract: Techniques for providing unified user interfaces among actively paired devices, including that first and second devices are actively paired together at a first time based on a determination that the first device is in physical proximity to the second device when the first and second devices are both authenticated for a same user service account; receiving, at the first time, an indication of an actuation of a first user interface control associated with a teleconferencing session and presented by the first device; and causing, in response the receipt of the indication and the determination that the first and second devices are actively paired together at the first time, a real-time component of the teleconferencing session to be rendered by the second device while a first user associated with the user service account is joined to the teleconferencing session as a participant.

Abstract: A data analysis system is disclosed that receives data from a master data system to enable useful and efficient rescheduling of items, taking into account effects of various rescheduling options on various metrics related to the items and/or the scheduling. The data analysis system includes sophisticated data analysis and interactive graphical user interface functionality to enable efficient, multi-variable evaluation of various rescheduling options. The interactive graphical user interface includes interactive functionality for suggesting rescheduling options in view of the effects of those changes on various metrics, evaluating various rescheduling options in view of effects on the various metrics, adjusting instances of metrics related to items/timelines in view of scheduling changes, and the like. Once a set of schedule modifications are determined by the data analysis system, the data analysis system can push the schedule modifications back to the master data system for implementation.

Abstract: Tamper-proofing and secure identity validation techniques in a transaction processing system and secure electronic payment techniques are disclosed. A tamper-proof transaction processing device is provided and comprises at least two different strength adhesives to secure parts of the device together and a housing comprising at least a first and second protective layer. An electronic component comprising a secure element chip storing unique information relating to the chip is located between the first and second protective layer in the housing. In another aspect, a transaction processing system includes a payment instrument that is configured to approve only negative value and/or zero value transaction requests. Another aspect provides an identity card checking system and method where the identity card is brought into proximity of a data processing device and identity information is displayed on the screen of the data processing device for the period of time while the card is in proximity.

Abstract: A messaging system, in one embodiment, can establish messaging accounts for a plurality of organizations (e.g., businesses) to allow customers or users of the organizations to conduct two-way messaging sessions between a customer and an organization. The messaging system can use a registration portal to allow an organization to set up a business/organization messaging account by providing account information. The account information can then be used to update one or more searchable databases that allow a customer to have multiple entry points into a messaging session with each of the registered businesses in the messaging system. For example, a search through a web browser or a map application can provide search results that contain or otherwise provide access to a selectable messaging option that is presented on a customer's device.

Abstract: A computer-implemented method and an apparatus for notifying customers of agent's availability is disclosed. An input indicative of a customer seeking an interaction with an agent of an enterprise is received on a first interaction channel. Subsequent to receiving the input, it is determined whether at least one agent is available for interacting with the customer. If no agent is available for interacting with the customer, a status message including an estimate of a waiting time for the interaction with the agent is provided to the customer. Subsequent to detecting the availability of the agent, a notification is provided to the customer for informing the customer of the availability of the agent. An interaction is facilitated between the customer and the agent subsequent to providing the notification to the customer. The interaction is facilitated on the first interaction channel or a second interaction channel different than the first interaction channel.

Abstract: A first device may receive a request to establish a replication session between a second device and a third device, where the replication session is associated with replicating user interactions with a user interface of an application across a first instance and a second instance of the application. The first device may receive, after receiving the request, information identifying a set of interactions by a user of the second device with a first user interface provided for display by the first instance. The first device may determine, from the information, a set of instructions related to causing an indication for the set of interactions to be provided for display on a second user interface provided for display for the second instance based on the information being received from the second device. The first device may provide, after determining the set of instructions, the set of instructions to the third device.

Abstract: State-of-satisfaction change pattern models each including a set of transition weights in state sequences of the states of satisfaction are obtained for predetermined change patterns of the states of satisfaction, and a state-of-satisfaction estimation model for obtaining the posteriori probability of the utterance feature amount given the state of satisfaction of an utterer is obtained by using the utterance-for-learning feature amount and a correct value of the state of satisfaction of an utterer who gave an utterance for learning corresponding to the utterance-for-learning feature amount. By using the input utterance feature amount and the state-of-satisfaction change pattern models and the state-of-satisfaction estimation model, an estimated value of the state of satisfaction of an utterer who gave an utterance corresponding to the input utterance feature amount is obtained.

Abstract: A Mobile Lawyer system includes a 360 degree HD video camera configured for mounting on a vehicle; a display screen configured for mounting inside the passenger compartment of a vehicle; and a Mobile Lawyer App downloaded and installed on a mobile telephone in communication with the video camera and display screen, configured, upon command from a user, to notify an attorney located remotely via a cellular and/or computer network, and to display a video image of the remote attorney on the display screen (or the screen of the mobile telephone), and to live-stream a 360 degree video captured by the video camera to the Internet for viewing by the remote attorney and for cloud storage. The introduction of a lawyer on-demand into a police encounter can help to defuse and de-escalate the situation. The lawyer can serve as a live observer, witness, and intermediary who can provide live legal guidance to the user.

Abstract: A system for generating a merged agent log starts with a processor receiving an audio signal of a communication session between a member-related client device and an agent client device. Processor processes the audio signal to generate caller utterances and generates identified tasks based on the caller utterances. The processor then generates caller utterance data including the identified tasks and a start time of the caller utterances and an end time of the caller utterances. The processor groups the caller utterances based on the identified tasks, and for each of the identified tasks, the processor generates an agent log using an agent logging neural network. The agent log is based on the caller utterances. Other embodiments are disclosed herein.

Abstract: A system for data recording across a network includes a session border controller connecting incoming data from the network to an endpoint recorder. A load balancer is connected to the network between the session border controller and the endpoint and receives the incoming data from the session border controller, wherein the load balancer comprises computer memory and a processor configured to parse the incoming data into video data and audio data according to identification protocols accessible by the processor from the computer memory. A recording apparatus includes recording memory that receives the incoming data from the load balancer, stores a duplicate version of the incoming data in the recording memory, and connects the incoming data to the endpoint.

Abstract: A device may receive audio data of a first call between a first user and a second user. The device may generate, based on the audio data, time series data associated with an audio signal of the first call and may process, using a first machine learning model, the time series data to generate first call insight information regarding one or more first insights associated with the first call. The device may process the audio data to generate image data associated with the audio signal and may process, using a second machine learning model, the image data to generate second call insight information regarding one or more second insights associated with the first call. The device may combine the first call insight information and the second call insight information to generate combined call insight information and cause an action to be performed based on the combined call insight information.

Abstract: Computing systems and methods are described in which video calls or other online communications are established or enhanced among two or more live participants. In some variants one or more preferences are gleaned from a first participant's behavior so as to streamline a call establishment with one or more qualified recipients. Alternatively or additionally, enriched auditory message data may be received privately from a sender without leaving a shared space.

Abstract: A computer-implemented method, comprising: receiving and storing, by a computer device, messages of one or more browsing sessions of a website in a first database; determining, by the computer device, whether one of the one or more browsing sessions is terminated; upon determining the one browsing session being terminated, fetching, by the computer device, the messages of the terminated browsing session; determining, by the computer device, one or more tags based at least on the messages of the terminated browsing session; and storing, by the computer device, the terminated browsing session with the one or more tags into a second database for data analysis.

Abstract: Data analysis, filter, and presentation techniques are described for an example call management system. An example method for a data management system includes receiving, from a user device, an account identifier of a first person, receiving, from the user device, a first message related to a topic of conversation to be discussed during a telephone call with the first person, determining, based on the account identifier and within a pre-determined time period, a presence of a set of data that describes conversation(s) from prior telephone call(s)/chat(s) with the first person, and sending, to a computer, at least some data from the set of data and a second message that indicates that the telephone call is mapped to a second person, where the computer is configured to display on a screen the second message and a presentation option that presents the at least some data via the computer.

Abstract: A computer-implemented method related to routing incoming interactions of contact centers. The method may include: receiving initial data identifying a first incoming interaction that includes information disclosing at least an intent of the first incoming interaction; and performing a first subprocess to generate a personalized routing profile tailored to facilitate routing the first incoming interaction in accordance with preferences of a first customer. The first subprocess may include: accessing data from a database, the database including at least a first customer profile storing data relating to the first customer; based on the accessed data and the intent of the first incoming interaction, determining preferred agent characteristics data of the first customer for the first incoming interaction; and generating the personalized routing profile so to include the preferred agent characteristics data of the first customer.

Abstract: Systems and methods are provided for providing search results. Social media posts are analyzed to identify a candidate for authoring an expert search thread, where one or more search terms are extracted from one or more social media posts of the candidate. The candidate is contacted to solicit an expert search thread, where the expert search thread solicited includes an identification of a plurality of links entered via a user interface by the expert that the expert identifies as being helpful to learning about a topic associated with the one or more search terms. The expert search thread is included in a set of search results prompted by one or more of the search terms.

Abstract: Systems, methods, and computer media for routing outbound contact requests are provided herein. The described examples allow routing and execution of outbound contact requests of different types, such as voice call, voice message, text message, chat, and email. Routing rules govern the routing of scheduled, automatic, and push-delayed outbound contact requests based on the type of outbound contact request and parameters associated with the request. Routing can include, for example, queuing a request for an agent, scheduling a request for release at a specified time, reserving a request for delayed push, or automatically executing an outbound contact event corresponding to the request.

Abstract: A conversation-based computing system may include a back-end computing module, a design module, and an execution module. The design module may be configured to provide a graphical user interface through which different conversation models are defined in metadata. Each model may include a topic containing respective goals, where the goals are associated with respective conversation flows that define respective dialogs that directs conversations toward the associated goals. Each model may also define references to topic-specific content stored in the back-end module. The execution module may be configured to execute a particular model between the system and a front-end computing device and set up integration of a live agent into the model. Execution of the model may involve, in part, carrying out, in an at least partially-automated fashion, the flow for the model according to the dialog, the topic-specific content corresponding to the model, and communicating using a specific communication protocol.

Abstract: Disclosed is an approach for allowing an entity to perform semantic analysis upon private data possessed by an enterprise, and to automatically perform categorization of that data for processing within the enterprise. A semantic API can be provided to allow the enterprise to provide the private data to a sematic analysis system, even when the semantic analysis system is configured as a multi-tenant system that handles other items of public or private data. A rules-based routing architecture may be provided to facilitate analysis and routing of analyzed messages to the appropriate destination within the organization.

Abstract: A computer-implemented method and system for enhancing interaction between a customer using a client computer and a customer service representative of a company using a workstation. A Web session is commenced on a Web site for the client computer of the customer, wherein the Web session includes displaying a first Web page to the customer. A telephonic interaction is commenced between the customer and the customer service representative and a split screen is displayed on the workstation. The split screen including the first Web page and a second Web page, wherein the second Web page is only viewable by the customer service representative. An application is caused to be moved from the second Web page to the first Web page for review and interaction by the customer via the client computer.

Abstract: An image processing system includes a server, an image processing device, a mobile terminal, and a call center terminal. When switching from a response by a chatbot to a response by an operator is executed, the server transmits a response history of the chatbot to the call center terminal so that the call center terminal may check the response history of the chatbot. The entire response history of the chatbot is presented to the operator when the amount of information on the response history of the chatbot is equal to or less than a predetermined threshold, and a summary of the response history based on the response history of the chatbot is presented to the operator when the amount of information on the response history of the chatbot is more than the threshold.

Abstract: A contact center, communication system, and method of operating a contact center are provided. In one example, the contact center includes a plurality of chatbots stored in memory and a chatbot selector that determines a customer interaction in the contact center will have a chatbot assigned thereto, selects a chatbot from the plurality of chatbots for assigning to the customer interaction based on a match between a capability of the chatbot and a service requirement associated with the customer interaction, and assigns the selected chatbot to the customer interaction thereby enabling the selected chatbot to process inputs received during the customer interaction and provide responses to the inputs.

Abstract: Methods for leveraging a plurality of machine-learning algorithms to improve a chat interaction are provided. The methods may include monitoring for initiation of a live chat session; alerting and assigning a chat responder to the live chat session; engaging one or more of a plurality of automated chat tools, the tools loaded with artificial intelligence (AI), in order to improve the response of the responder during the session; reviewing and retrieving, using the AI, from a machine learning (ML) library in electronic communication with the AI, historical information; presenting, on a chat responder screen, selected actionable information generated based on the historical information, to the responder; integrating, based on pre-determined conditions, chat responses into the ML library; and integrating into the ML library, based on the same or other pre-determined conditions, chat comments. The chat comments are generated by a chat initiator.

Abstract: The present invention provides a method, system, and computer program product of managing and displaying online messages along timelines. In an embodiment, the present invention includes receiving a plurality of online messages from an online website, determining sets of similar online messages among the plurality of online messages, and displaying on a computer display each of the sets of similar online messages along a graphical representation of a timeline corresponding to the each of the sets of similar online messages, resulting in displayed timelines and displayed online messages. In a further embodiment, the present invention includes in response to receiving a new online message from the online website, determining each set among the sets of similar online messages to which the new online message is similar, and displaying on the computer display the new online message, resulting in a displayed new online message.

Abstract: A computerized method for evaluating agent-call-logging, in a contact center, is provided herein. The method includes operating an evaluating agent-call-logging module. The operating of an evaluating agent-call-logging module includes: (i) receiving a recorded interaction between an agent and a customer, stored in the database of recorded interactions and a corresponding agent-call-logging, having ‘n’ sentences, stored in the database of call loggings; (ii) operating a speech-to-text algorithm on the received recorded interaction to yield a summarized text thereof. The yielded summarized text is comprised of sentences expressed by the customer; and (iii) operating a semantic comparison unit, to compare each sentence in the yielded summarized text with a corresponding sentence in the agent-call-logging, to yield a Sentence Similarity Score (SSS) for each sentence of the agent-call-logging.

Abstract: A computerized-method for providing real-time lockless parallel screen recording compliance enforcement to omni-channel cloud systems, is provided herein. In a processor of a client computer configured to execute code for recording events of one or more voice or digital interactions, on one or more screens associated to the client computer, the computerized-method maintains a cache for storing a masked state. Each interaction is having an associated interaction identifier and upon receiving a screen event from a server of a cloud-based video recording that is communicating with the client computer over a communication network, operating a compliance-enforcement module. The compliance-enforcement module includes updating the cache; and operating a module of recording of screen events for the screen events of the one or more voice or digital interactions. Thus, by updating in real-time the cache on the client computer refraining from database locks in the server of the cloud-based video recording.

Abstract: In one embodiment, a method includes receiving a user input from a client system associated with a user, determining a task based on the user input and a confidence score associated with the task, generating one or more first dialog acts based on a task policy which specifies dialog acts associated with the task, generating one or more second dialog acts based on an override policy responsive to the confidence score being less than a threshold score, wherein the override policy specifies dialog acts that modify dialog acts specified by the task policy; and sending instructions for presenting a response to the user input to the client system, wherein the response is based on one or more of the first dialog acts or the second dialog acts.

Abstract: A method of establishing bearers for a device in a wireless communication network, including collecting for the device data over a period of time from communication sessions the device participates in, at least some of the communication sessions being supported by a default bearer and a dedicated bearer; calculating from the collected data a likelihood a dedicated bearer will be established for the device at one or more different times values, and predicting the dedicated bearer will be established for the device at a time value if the likelihood of establishment at that time value exceeds a specified threshold; and initiating establishment of the dedicated bearer to establish the dedicated bearer for the predicted time value.

Abstract: A system, method, and computer-readable medium for performing a customer service interaction estimation operation, comprising: training a customer service interaction estimation system using a training dataset of cases to provide a trained predictive model; identifying current open cases via the customer service interaction system; applying the trained predictive model to the current open cases to identify low customer experience cases; generating an estimation output relating to the current open cases, the estimation output identifying an open case subset of cases having a high risk of high effort to resolve.

Abstract: A contact center network including a contact center unit connected via a communication network to a plurality of agents and to a plurality of IoT devices, wherein each one of the plurality of IoT devices is equipped with sensor devices adapted to measure predetermined IoT measurement data, and at least one actuator device adapted to control the IoT device remotely, wherein the contact center unit is connectable to the sensor devices and the actuator devices via a IoT middleware unit adapted to receive an incident notification, if sensor measurement data matches a predetermined criterion indicating an incident, and wherein the contact center unit includes a routing unit adapted to route a contact based on the incident information comprised in the incident notification to an agent. Further, embodiments relate to a method for establishing a communication session in a contact center network.

Abstract: Method starts with processing, by a processor, audio signal to generate audio caller utterance. Processor generates an agent action ranking score associated with the audio caller utterance and determines whether the agent action ranking score is below a minimum threshold. In response to determining that the agent action ranking score is below the minimum threshold, processor generates a transcribed caller utterance using a speech-to-text processor and generates an identified task based on the transcribed caller utterance. Using the transcribed caller utterance and a task-specific agent coaching neural network associated with the identified task, processor generates an ideal response. Processor generates a feedback result and causes the feedback result to be displayed on a display device of the agent client device. Other embodiments are disclosed herein.

Abstract: Systems and methods for continuous processing of unstructured data streams are provided. Information may be stored in memory regarding a query, including associated search results and statistics derived at an identified time. After the identified time, unstructured data may be received from a plurality of streams over a communication network. A full-text search may be conducted on the received unstructured data based on the query to yield one or more matches. The stored statistics associated with the query may be retrieved from memory and updated based on the search results of the unstructured data received at the subsequent time. The updated statistics may then be stored in memory for retrieval at a subsequent time.

Abstract: Method starts with processing, by processor, receiving audio signal of communication session between member-related client device and agent client device. Processor processes audio signal to generate caller utterances, each including audio caller utterance and transcribed caller utterance. Caller utterances includes first and second caller utterances. For each of the plurality of caller utterances, processor generates relationship data based on transcribed caller utterance, generates identified task based on transcribed caller utterance, and generates task completion probability result based on audio caller utterance, relationship data, and identified task, and stores the task completion probability result in a database. Processor computes agent action ranking score that is based on difference between task completion probability result of first caller utterance and task completion probability result of second caller utterance that precedes first caller utterance.

Abstract: This invention relates to a method of processing sensitive information over VoIP. The method provides a method of processing, by a call processor, a media call comprising the steps of: receiving a first signalling stream from a first entity; creating a second signalling stream to a second entity; forwarding signals received from the first signalling stream to the second signalling stream; receiving a third signalling stream from the second entity; creating a fourth signalling stream to the first entity; and forwarding signals received on the third signalling stream to the fourth signalling stream; the first signalling stream containing instructions to set up a media call between the first entity and the second entity such that media is transmitted over a first media stream from the first entity to the second entity and a media is transmitted over a second media stream from the second entity to the first entity without intervention by said call processor.

Abstract: A computer-implemented process includes receiving an incoming contact at a contact center from a user; identifying a plurality of different portions of the incoming contact, each of a plurality of portions associated with a respective topic; and for each of the different portions, routing that different portion to a respective agent of the contact center based on its associated respective topic. Furthermore, the process includes receiving a respective response from one or more of the respective agents, the respective response pertaining to the different portion routed to that agent; combining the respective response from the one or more of the respective agents to form a first composite response; and forwarding the first composite response to the user.

Abstract: A method for summarizing dialogs may include obtaining an agent text stream and a customer text stream, segmenting the agent text stream and customer text stream into sentences, and labeling sentences associated with the segmented agent text stream and the segmented customer text stream. The method may further include extracting sentences from the agent text stream and the customer text stream based upon frequencies of appearance of words and terms of interest; generating an agent summary paragraph based on the extracted sentences from the agent text stream, and generating a customer summary paragraph based on the extracted sentences from the customer text stream. The method may identify keywords associated with each of the agent summary paragraph and the customer summary paragraph.